edgegate_llm_compile
Submit a multi-component LLM compile and link job via Qualcomm AI Hub, returning a job ID to poll for status.
Instructions
Submit a multi-component LLM compile + link job via Qualcomm AI Hub. Returns a compile_job_id; poll with edgegate_check_llm_compile_status. Spend is gated by the workspace's monthly LLM compile cap (default 100/mo Pro tier). Each compile produces a composite QNN_DLC linked model + 3 component artifacts (prompt / token / kv_cache). Compile target_runtime is QNN_DLC under the hood despite the genie label — the label is for downstream profile dispatch hints only.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"workspace_id": "<workspace_id>",
"source_artifact_ids": "<source_artifact_ids>",
"device_id": "<device_id>"
},
"name": "edgegate_llm_compile"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| roles | No | ||
| device_id | Yes | ||
| workspace_id | Yes | ||
| target_runtime | No | genie | |
| context_lengths | No | ||
| sequence_lengths | No | ||
| source_artifact_ids | Yes |